Qwen3 235B-A22B Instruct 2507 pricing & specs

Alibaba (Qwen) · released 2025-07-21 · ● verified 2026-10-11

input / 1M$0.09via DeepInfra
output / 1M$0.55via DeepInfra
context262.1K
max output16.4K

// price history ($/1M tokens)

$0.6325
input $/1Moutput $/1M2025-07-21 → 2026-10-11

// cheaper or similar alternatives

modelinoutctxvs Qwen3 235B-A22B Instruct 2507
Gemma 4 E2B IT$0.04$0.08131.1K−75.6%
Qwen3.7 Flash$0.03$0.131M−73.2%
Gemma 3 12B IT$0.05$0.10131.1K−69.5%
Qwen Turbo$0.05$0.201M−57.3%
DeepSeek V4 Flash 0731$0.06$0.181.05M−56.1%

// price by host

hostin $/1Mout $/1M
DeepInfra$0.09$0.55
Amazon Bedrock$0.22$0.88

// faq

How much does Qwen3 235B-A22B Instruct 2507 cost?

Qwen3 235B-A22B Instruct 2507 costs $0.09 per million input tokens and $0.55 per million output tokens (cheapest tracked host: DeepInfra). At 50M input and 10M output tokens per month that is about $10.00.

What is the context window of Qwen3 235B-A22B Instruct 2507?

262.1K tokens, with up to 16.4K output tokens per request.

What are cheaper alternatives to Qwen3 235B-A22B Instruct 2507?

Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Gemma 3 12B IT ($0.05 in / $0.10 out) offer the same input types and capabilities for less.

Is Qwen3 235B-A22B Instruct 2507 open weights?

Yes. It is available from 2 tracked hosts; the cheapest is DeepInfra at $0.09 input and $0.55 output per million tokens.

// spec sheet

input / 1M
$0.09
output / 1M
$0.55
blended (3:1)
$0.205
context
262.1K
max output
16.4K
input types
text
reasoning
no
tool calling
yes
structured output
yes
open weights
yes
knowledge cutoff
n/a
price source
DeepInfra

report a data error

// cost calculator

modelin $/1Mout $/1M= monthly
Gemma 4 E2B IT$0.04$0.08$2.80
Qwen3.7 Flash$0.03$0.13$2.80
Gemma 3 12B IT$0.05$0.10$3.50
Qwen3 235B-A22B Instruct 2507$0.09$0.55$10.00

Base-tier list prices. Long-context tiers, caching and batch discounts are not included.